ekdgcmgbnoejccbbdoaokppjcpljpfil
Prompt injection detection for autonomous agents — powered by vard 🛡️ OpenClaw Guardrails — Security Toolkit for Autonomous AI Agents AI agents browse, click, and act on your behalf. OpenClaw Guardrails makes sure they only do what you intended. ⚡ Real-Time Prompt Injection Detection Pages are scanned as your agent encounters them. Detects instruction overrides, role manipulation, delimiter injection, encoding attacks, and system prompt leak attempts. Visual warnings appear directly on the page so threats are impossible to miss. 🚫 Agent Action Blocking Automatically hides dangerous action buttons — like sending emails or submitting forms.Your agent can't do what it can't see. 🌐 Custom Site Controls Whitelist sites you trust. Blocklist sites you don't. Domain-level control over where your agent is allowed to operate freely. 📋 Local Scan History Every scan is logged locally so you can review what was detected, when, and where. Full audit trail, zero cloud dependency. 🔒 Configurable Severity Thresholds Decide what level of threat triggers a warning vs. a hard block. Tune the guardrails to match your risk tolerance. 100% local. Zero data leaves your browser. All scanning runs on-device using the Vard detection library. No page content is ever transmitted externally. We don't collect, store, or share any browsing data. Settings and history stay in local storage, fully under your control. OpenClaw Guardrails is an independent project and is not affiliated with the opensource project OpenClaw, but is designed to assist users of OpenClaw as well as all other types of autonomous agent.
ClawPost
Secure posting for AI agents. Pairs with Claw Post REST or MCP (Streamable HTTP + OAuth). Claw Post let's your AI agent post to social media platforms using your browser and logged in session. No API keys, no credential sharing, no brittle scripts. ~1¢ per post. No token burn. How it works: 1. Sign up at clawpost.net 2. Install the extension 3. Pair extension by logging into chrome profile or with Pairing code 4. Give your agent the API key and SKILL.MD. Built for developers and teams running AI workflows. Simple REST API, queue-based delivery, retries, idempotency, and media support. One API call to post. Start free. Paid plans for higher volume.
OpenClaw Token Monitor
OpenClaw calculates real-time token usage and enforces strict AI budget limits. OpenClaw Token Monitor is the ultimate enterprise-grade budget protector and real-time expenditure tracker for AI enthusiasts, developers, and power users. If you use AI agents or tools, OpenClaw ensures you never face an unexpected bill again. Managing API costs across multiple providers can be a nightmare. OpenClaw Token Monitor acts as a high-performance "kill-switch," sitting between your browser and AI endpoints to calculate every token in real-time. Whether you are using OpenAI, Anthropic, or OpenRouter, OpenClaw gives you total financial control. Core Features: Real-Time Token Calculation: Instantly calculates prompt and completion tokens as requests are made. Hard Budget Kill-Switch: Automatically blocks API requests the millisecond you hit your pre-set dollar limit. Multi-Provider Support: Seamlessly monitors OpenAI (GPT-4o/o1), Anthropic (Claude 3.5), Google Gemini, and OpenRouter. Custom Rate Pricing: Manually set your own "In" and "Out" token rates to match your specific API tier or discounted pricing. Visual Progress Tracking: A sleek, "Lobster-inspired" glassmorphism dashboard showing your session spend, token count, and active model. Privacy-First Architecture: Your data never leaves your machine. All calculations and storage happen locally on your browser. How to Use: 1. Install OpenClaw Token Monitor. 2. Set Your Budget: Open the settings () and enter your maximum spend. 3. Define Rates: Input the current pricing for your preferred models. 4. Work with Confidence: Watch the live "Claw" monitor your session. If you hit 100%, the kill-switch activates!
OpenClaw Context Bridge
Connect your browser to your OpenClaw AI agent. Clip content, get page context, automate workflows. OpenClaw Context Bridge gives your browser a direct line to OpenClaw. Clip the entire current page (URL, title, and rich page context) in one click Paste or type any input and send it as user context to your OpenClaw workflow Stay fast and focused with a minimal, clean popup Built for people who work with AI assistants daily and want less copying, less switching, and better context transfer. Perfect for: Research capture Page-to-agent handoff Quick notes, prompts, and task inputs Workflow automation via your OpenClaw setup Requirements: You must have access to your OpenClaw gateway through Tailscale Configure your gateway URL and optional token in the extension settings
OpenClaw Browser Relay - Powered by PaioClaw
Attach OpenClaw (Powered by PaioClaw) to your existing Chrome tab via a remote CDP relay server OpenClaw Browser Relay - Powered by PaioClaw is a high-performance bridge designed to connect your browser tabs directly to your AI agent (OpenClaw, MoltBot, or ClawdBot) via a remote Chrome DevTools Protocol (CDP) relay server. By utilizing the power of the debugger API, this extension allows your AI assistant to programmatically interact with web pages, clicking elements, typing text, and navigating—enabling sophisticated browser automation with a single click. Getting started with PaioClaw and OpenClaw is simple. Follow these steps to link your browser: 1. Install & Open Options: After installation, the options page will open automatically, or you can right-click the extension icon and select "Options". 2. Retrieve Credentials: (You need to signup for a free PaioClaw account) - Sign in to your PaioClaw Dashboard. - Once Signed Up, Select Server/Agent which you want to interact with browser. - Click the Connect with PaioClaw button. - The status indicator will show "You're all set! PaioClaw is now connected" once the handshake is successful. 4. Run the Agent: - Navigate to the tab you wish to automate. - Click the PaioClaw icon in your Chrome extension toolbar to attach the agent and begin your workflow. - One-Click Attachment: Quickly attach or detach the AI agent from your active tab via the extension toolbar icon. - Seamless Navigation: Features an intelligent re-attachment system that maintains your session even after page refreshes or site navigation. - Visual Status Indicators: Stay informed with real-time badges indicating connection states: Connected (ON), Connecting (…), or Error (!). - Multi-Tab Support: Capable of managing multiple automated sessions, including creating and closing targets via the AI agent. - Privacy-First Design: All configuration data is stored locally, and automation data is sent only to your specified gateway.
